集成视觉显著性和群决策的航空零件孔特征检测

田佳淳; 王亮; 梅标; 朱伟东

doi:10.37188/OPE.20243201.0125

您当前的位置：

首页 >

文章列表页 >

集成视觉显著性和群决策的航空零件孔特征检测

信息科学 | 更新时间：2024-01-13

- 集成视觉显著性和群决策的航空零件孔特征检测
- Hole feature detection for aircraft parts by integrating visual saliency and group decision making
- 光学精密工程 2024年32卷第1期页码：125-136
- 作者机构：
  
  1.浙江大学工程师学院，浙江杭州 310015
  2.中航西安飞机工业集团股份有限公司，陕西西安 710089
  3.中国科学院福建物质结构研究所泉州装备制造研究中心，福建泉州 362100
  4.浙江大学机械工程学院，浙江杭州 310058
- 作者简介：
  
  [ "田佳淳（2000-），男，江苏启东人，硕士研究生，2022年于南京航空航天大学获得学士学位，主要从事机器视觉、图像处理等方面的研究。E-mail： a_tianjiachun@zju.edu.cn" ]
  [ "梅标（1984-），男，安徽宿州人，助理研究员，2016年于浙江大学获得博士学位，主要从事智能制造、机器视觉等方面的研究。E-mail： mechme@126.com" ]
- 基金信息：
  
  浙江省“尖兵”“领雁”研发攻关计划资助项目(2022C01134);杭州市重大科技创新项目资助(2022AIDZ0026);国家自然科学基金资助项目(51675479)
- DOI：10.37188/OPE.20243201.0125
  中图分类号：
扫描看全文
田佳淳,王亮,梅标等.集成视觉显著性和群决策的航空零件孔特征检测[J].光学精密工程,2024,32(01):125-136.

TIAN Jiachun,WANG Liang,MEI Biao,et al.Hole feature detection for aircraft parts by integrating visual saliency and group decision making[J].Optics and Precision Engineering,2024,32(01):125-136.
田佳淳,王亮,梅标等.集成视觉显著性和群决策的航空零件孔特征检测[J].光学精密工程,2024,32(01):125-136. DOI： 10.37188/OPE.20243201.0125.

TIAN Jiachun,WANG Liang,MEI Biao,et al.Hole feature detection for aircraft parts by integrating visual saliency and group decision making[J].Optics and Precision Engineering,2024,32(01):125-136. DOI： 10.37188/OPE.20243201.0125.

摘要

为了实现复杂环境下航空零件孔特征的高效高精度检测，提出了一种集成视觉显著性和群决策的检测方法。在经典FT显著性检测算法中引入图像增强步骤，并为每个像素赋予以最大显著区域中心为参考的权重，使用改进后的方法对图像进行孔区域分割。设计具有多尺度多结构元素的新型数学形态学边缘检测算法，结合轮廓细化算法对孔区域进行轮廓提取。最后，利用Meanshift算法寻找轮廓点的圆心位置，建立新的基于群决策的圆半径计算模型，获得孔特征的关键几何参数。结果表明：改进的视觉显著性特征检测算法能够生成更加突显孔特征的全分辨率显著图；新型数学形态学边缘检测算法能获得简化且可靠的轮廓点；该方法在不均匀光照、各类孔缺陷和孔内壁干扰等条件下均显示出较好的稳定性；即使在噪声密度高达30%时仍能成功完成孔检测，且圆心坐标和半径的误差均小于0.012 mm；平均检测时间仅为0.236 s。该方法能够在复杂环境下对航空零件孔特征进行准确、稳定的检测。

Abstract

A detection method integrating visual saliency and group decision making was proposed with the aim of achieving efficient and high-precision detection of hole features in aircraft parts in complex environments. First， an image enhancement step was incorporated into the classical frequency-tuned （FT） saliency detection algorithm， and each pixel was assigned a weight based on the center of the maximum saliency region. This improved method was used for hole region segmentation. Second， a novel mathematical morphological edge detection algorithm with multi-scale and multi-structural elements was designed. This algorithm was combined with contour thinning to extract hole contours. Finally， the centroid positions of the contour points were obtained using the Meanshift algorithm and a new model based on group decision making was established for calculating the hole radius， thus obtaining key geometric parameters of the hole features. The results show that the improved visual saliency feature detection algorithm generates higher-resolution saliency maps that highlight hole features more prominently. This novel mathematical morphological edge detection algorithm obtains simplified and reliable contour points. It also exhibits a high robustness under complex conditions， including uneven lighting， various types of hole defects， and interference from the hole interior. This method can still perform hole detection successfully even with a noise density of up to 30%， and the errors in the coordinates of the center and the radius are less than 0.012 mm. The average detection time is only 0.236 s. It can accurately and robustly detect hole features in aircraft parts in complex environments.

关键词

航空零件孔特征检测显著性检测数学形态学群决策

Keywords

aircraft parthole feature detectionsaliency detectionmathematical morphologygroup decision making

references

MEI B， LIANG Z， ZHU W， et al. Positioning variation synthesis for an automated drilling system in wing assembly［J］. Robotics and Computer-Integrated Manufacturing， 2021， 67： 102044. doi: 10.1016/j.rcim.2020.102044http://dx.doi.org/10.1016/j.rcim.2020.102044

GAO P P， LIU F， SUN X Z， et al. Rapid non-contact visual measurement method for key dimensions of revolving workpieces［J］. International Journal of Metrology and Quality Engineering， 2021， 12： 10. doi: 10.1051/ijmqe/2021008http://dx.doi.org/10.1051/ijmqe/2021008

张太恒，梅标，乔磊，等. 纹理边界引导的复合材料圆孔检测方法［J］. 浙江大学学报（工学版）， 2020， 54（12）： 2294-2300.

ZHANG T H， MEI B， QIAO L， et al. Detection method for composite hole guided by texture boundary［J］. Journal of Zhejiang University （Engineering Science）， 2020， 54（12）： 2294-2300.（in Chinese）

YU L， BI Q， JI Y， et al. Vision based in-process inspection for countersink in automated drilling and riveting［J］. Precision Engineering， 2019， 58： 35-46. doi: 10.1016/j.precisioneng.2019.05.002http://dx.doi.org/10.1016/j.precisioneng.2019.05.002

LOU H C， LU M， CUI H H， et al. High-precision location for occluded reference hole based on robust extraction algorithm［J］. Measurement Science and Technology， 2021， 32（3）： 035021. doi: 10.1088/1361-6501/abb165http://dx.doi.org/10.1088/1361-6501/abb165

王冬云，唐楚，鄂世举，等. 基于导向滤波Retinex和自适应Canny的图像边缘检测［J］. 光学精密工程， 2021， 29（2）： 443-451. doi: 10.37188/OPE.20212902.0443http://dx.doi.org/10.37188/OPE.20212902.0443

WANG D Y， TANG CH， E SH J， et al. Image edge detection based on guided filter Retinex and adaptive Canny［J］. Optics and Precision Engineering， 2021， 29（2）： 443-451.（in Chinese）. doi: 10.37188/OPE.20212902.0443http://dx.doi.org/10.37188/OPE.20212902.0443

李梦霞，曹博，卢佳玮，等. 数学形态学区域分割的快速相位解包裹算法［J］. 光学精密工程， 2021， 29（11）：2724-2733. doi: 10.37188/OPE.20212911.2724http://dx.doi.org/10.37188/OPE.20212911.2724

LI M X， CAO B， LU J W， et al. Fast phase unwrapping algorithm based on region segmenting with mathematical morphology［J］. Optics and Precision Engineering， 2021， 29（11）：2724-2733. （in Chinese）. doi: 10.37188/OPE.20212911.2724http://dx.doi.org/10.37188/OPE.20212911.2724

JIAN M， WANG J， YU H， et al. Visual saliency detection by integrating spatial position prior of object with background cues［J］. Expert Systems With Applications， 2021， 168： 114219. doi: 10.1016/j.eswa.2020.114219http://dx.doi.org/10.1016/j.eswa.2020.114219

HOU X D， ZHANG L Q. Saliency detection： a spectral residual approach［C］. 2007 IEEE Conference on Computer Vision and Pattern Recognition. June 17-22， 2007. Minneapolis， MN， USA. IEEE， 2007： 1-8.

ACHANTA R， HEMAMI S， ESTRADA F， et al. Frequency-tuned salient region detection［C］. 2009 IEEE Conference on Computer Vision and Pattern Recognition. June 20-25， 2009. Miami， FL. IEEE， 2009： 1597-1604.

YANG C， ZHANG L H， LU H C， et al. Saliency detection via graph-based manifold ranking［C］. 2013 IEEE Conference on Computer Vision and Pattern Recognition. June 23-28， 2013. Portland， OR， USA. IEEE， 2013： 3166-3173.

YANG S， LIN G， JIANG Q， et al. A Dilated Inception Network for Visual Saliency Prediction［EB/OL］. 2019： arXiv： 1904.03571. https：//arxiv.org/abs/1904.03571.pdfhttps://arxiv.org/abs/1904.03571.pdf. doi: 10.1109/tmm.2019.2947352http://dx.doi.org/10.1109/tmm.2019.2947352

王向军，李名洋，王霖，等. 边缘信息引导多级尺度特征融合的显著性目标检测方法［J］. 红外与激光工程， 2023， 52（1）： 261-270.

WANG X J， LI M Y， WANG L， et al. Salient object detection method based on multi-scale feature-fusion guided by edge information［J］. Infrared and Laser Engineering， 2023， 52（1）： 261-270. （in Chinese）

XIE Q， LU D， DU K， et al. Aircraft skin rivet detection based on 3D point cloud via multiple structures fitting［J］. Computer-Aided Design， 2020， 120： 102805. doi: 10.1016/j.cad.2019.102805http://dx.doi.org/10.1016/j.cad.2019.102805

CHENG Y Z. Mean shift， mode seeking， and clustering［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 1995， 17（8）： 790-799. doi: 10.1109/34.400568http://dx.doi.org/10.1109/34.400568

KOOHPAYEGANI S A， TEJANKAR A， PIRSIAVASH H. Mean Shift for Self-supervised Learning［EB/OL］. 2021： arXiv： 2105.07269. https：//arxiv.org/abs/2105.07269.pdfhttps://arxiv.org/abs/2105.07269.pdf. doi: 10.1109/iccv48922.2021.01016http://dx.doi.org/10.1109/iccv48922.2021.01016

ZHAO M， JHA A， LIU Q， et al. Faster Mean-shift： GPU-accelerated clustering for cosine embedding-based cell segmentation and tracking［J］. Medical Image Analysis， 2021， 71： 102048. doi: 10.1016/j.media.2021.102048http://dx.doi.org/10.1016/j.media.2021.102048

BHAT P G， SUBUDHI B N， VEERAKUMAR T， et al. Target tracking using a mean-shift occlusion aware particle filter［J］. IEEE Sensors Journal， 2021， 21（8）： 10112-10121. doi: 10.1109/jsen.2021.3054815http://dx.doi.org/10.1109/jsen.2021.3054815

ZHANG Z， LI Z L. Personalized individual semantics-based consistency control and consensus reaching in linguistic group decision making［J］. IEEE Transactions on Systems， Man， and Cybernetics： Systems， 2022， 52（9）： 5623-5635. doi: 10.1109/tsmc.2021.3129510http://dx.doi.org/10.1109/tsmc.2021.3129510

陈顺，李登峰. 融合Canny算子和形态学的齿轮图像边缘检测研究［J］. 机电工程， 2020， 37（7）：821-825. doi: 10.3969/j.issn.1001-4551.2020.07.016http://dx.doi.org/10.3969/j.issn.1001-4551.2020.07.016

CHEN SH， LI D F. Edge detection of gear image based on Canny operator and morphology［J］. Mechanical & Electrical Engineering Magazine， 2020， 37（7）：821-825. （in Chinese）. doi: 10.3969/j.issn.1001-4551.2020.07.016http://dx.doi.org/10.3969/j.issn.1001-4551.2020.07.016

TANG Y， HE L， LU W， et al. A novel approach for fracture skeleton extraction from rock surface images［J］. International Journal of Rock Mechanics and Mining Sciences， 2021， 142： 104732. doi: 10.1016/j.ijrmms.2021.104732http://dx.doi.org/10.1016/j.ijrmms.2021.104732

DE GIOIA F， MEONI G， GIUFFRIDA G， et al. A robust RANSAC-based planet radius estimation for onboard visual based navigation［J］. Sensors， 2020， 20（14）： 4041. doi: 10.3390/s20144041http://dx.doi.org/10.3390/s20144041

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

数学形态学区域分割的快速相位解包裹算法

结合分数阶显著性检测及量子烟花算法的NSST域图像融合

半透明胶条表面光条中心线提取

结合Retinex校正和显著性的主动轮廓图像分割

光学遥感图像中复杂海背景下的舰船检测